Iterative RLHF collapses because policies exploit reward-model blind spots in the feedback loop; foresighted policy optimization restores the missing influence term and prevents the collapse.
Figure 3 demonstrates that standard RLHF policies increasingly exploit noise dimensions, achieving high proxy rewards but abandoning true utility
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explaining and Preventing Alignment Collapse in Iterative RLHF
Iterative RLHF collapses because policies exploit reward-model blind spots in the feedback loop; foresighted policy optimization restores the missing influence term and prevents the collapse.